| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 71.36150234741784, | |
| "global_step": 7600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.8199999999999998e-05, | |
| "loss": 9.9485, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 5.82e-05, | |
| "loss": 5.4005, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 3.5134339332580566, | |
| "eval_runtime": 29.4124, | |
| "eval_samples_per_second": 7.242, | |
| "eval_steps_per_second": 0.918, | |
| "eval_wer": 0.9822416974169742, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 8.819999999999999e-05, | |
| "loss": 3.2998, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0001182, | |
| "loss": 3.0848, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 3.0378262996673584, | |
| "eval_runtime": 29.389, | |
| "eval_samples_per_second": 7.248, | |
| "eval_steps_per_second": 0.919, | |
| "eval_wer": 0.9822416974169742, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.0001482, | |
| "loss": 3.0465, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.00017819999999999997, | |
| "loss": 3.0385, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_loss": 3.0117852687835693, | |
| "eval_runtime": 29.166, | |
| "eval_samples_per_second": 7.303, | |
| "eval_steps_per_second": 0.926, | |
| "eval_wer": 0.9822416974169742, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 0.00020819999999999996, | |
| "loss": 3.0281, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.0002382, | |
| "loss": 2.9897, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "eval_loss": 2.9294049739837646, | |
| "eval_runtime": 29.3884, | |
| "eval_samples_per_second": 7.248, | |
| "eval_steps_per_second": 0.919, | |
| "eval_wer": 0.9822416974169742, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.00026819999999999996, | |
| "loss": 2.5043, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 0.0002982, | |
| "loss": 1.4181, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "eval_loss": 0.9793046116828918, | |
| "eval_runtime": 29.05, | |
| "eval_samples_per_second": 7.332, | |
| "eval_steps_per_second": 0.929, | |
| "eval_wer": 0.9068265682656826, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 0.00029852664576802507, | |
| "loss": 1.044, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 0.0002969592476489028, | |
| "loss": 0.8274, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "eval_loss": 0.6433392763137817, | |
| "eval_runtime": 29.4518, | |
| "eval_samples_per_second": 7.232, | |
| "eval_steps_per_second": 0.917, | |
| "eval_wer": 0.6335332103321033, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 0.00029539184952978055, | |
| "loss": 0.7475, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 0.0002938244514106583, | |
| "loss": 0.6117, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "eval_loss": 0.5542563796043396, | |
| "eval_runtime": 29.4264, | |
| "eval_samples_per_second": 7.238, | |
| "eval_steps_per_second": 0.918, | |
| "eval_wer": 0.566420664206642, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 0.00029225705329153604, | |
| "loss": 0.5792, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 0.0002906896551724138, | |
| "loss": 0.4713, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "eval_loss": 0.5372164845466614, | |
| "eval_runtime": 29.4964, | |
| "eval_samples_per_second": 7.221, | |
| "eval_steps_per_second": 0.915, | |
| "eval_wer": 0.5166051660516605, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 0.0002891222570532915, | |
| "loss": 0.4702, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 0.00028755485893416926, | |
| "loss": 0.4045, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "eval_loss": 0.49404770135879517, | |
| "eval_runtime": 29.3183, | |
| "eval_samples_per_second": 7.265, | |
| "eval_steps_per_second": 0.921, | |
| "eval_wer": 0.4534132841328413, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 0.000285987460815047, | |
| "loss": 0.3913, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 0.00028442006269592475, | |
| "loss": 0.3514, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "eval_loss": 0.4763822853565216, | |
| "eval_runtime": 29.42, | |
| "eval_samples_per_second": 7.24, | |
| "eval_steps_per_second": 0.918, | |
| "eval_wer": 0.4432656826568266, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 0.0002828526645768025, | |
| "loss": 0.3558, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 0.00028128526645768024, | |
| "loss": 0.333, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "eval_loss": 0.4512215554714203, | |
| "eval_runtime": 29.3921, | |
| "eval_samples_per_second": 7.247, | |
| "eval_steps_per_second": 0.919, | |
| "eval_wer": 0.4232011070110701, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "learning_rate": 0.000279717868338558, | |
| "loss": 0.3235, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 0.0002781504702194357, | |
| "loss": 0.2939, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "eval_loss": 0.4824497699737549, | |
| "eval_runtime": 29.3229, | |
| "eval_samples_per_second": 7.264, | |
| "eval_steps_per_second": 0.921, | |
| "eval_wer": 0.42273985239852396, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 11.74, | |
| "learning_rate": 0.00027658307210031346, | |
| "loss": 0.2949, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 0.0002750156739811912, | |
| "loss": 0.2593, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "eval_loss": 0.4765360653400421, | |
| "eval_runtime": 29.1743, | |
| "eval_samples_per_second": 7.301, | |
| "eval_steps_per_second": 0.925, | |
| "eval_wer": 0.40751845018450183, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 12.68, | |
| "learning_rate": 0.00027344827586206895, | |
| "loss": 0.2675, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 13.15, | |
| "learning_rate": 0.0002718808777429467, | |
| "loss": 0.2433, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 13.15, | |
| "eval_loss": 0.4478711187839508, | |
| "eval_runtime": 29.2927, | |
| "eval_samples_per_second": 7.271, | |
| "eval_steps_per_second": 0.922, | |
| "eval_wer": 0.3863007380073801, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 13.62, | |
| "learning_rate": 0.00027031347962382443, | |
| "loss": 0.2233, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 0.0002687460815047022, | |
| "loss": 0.23, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "eval_loss": 0.45760419964790344, | |
| "eval_runtime": 29.3313, | |
| "eval_samples_per_second": 7.262, | |
| "eval_steps_per_second": 0.921, | |
| "eval_wer": 0.39990774907749077, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 0.0002671786833855799, | |
| "loss": 0.2054, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 0.00026561128526645766, | |
| "loss": 0.2077, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "eval_loss": 0.4995218515396118, | |
| "eval_runtime": 29.3519, | |
| "eval_samples_per_second": 7.257, | |
| "eval_steps_per_second": 0.92, | |
| "eval_wer": 0.39275830258302585, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 0.0002640438871473354, | |
| "loss": 0.223, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 15.96, | |
| "learning_rate": 0.00026247648902821315, | |
| "loss": 0.1775, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 15.96, | |
| "eval_loss": 0.4842701554298401, | |
| "eval_runtime": 29.4414, | |
| "eval_samples_per_second": 7.235, | |
| "eval_steps_per_second": 0.917, | |
| "eval_wer": 0.39321955719557194, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 16.43, | |
| "learning_rate": 0.0002609090909090909, | |
| "loss": 0.1818, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "learning_rate": 0.00025934169278996863, | |
| "loss": 0.1893, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "eval_loss": 0.47495996952056885, | |
| "eval_runtime": 29.1664, | |
| "eval_samples_per_second": 7.303, | |
| "eval_steps_per_second": 0.926, | |
| "eval_wer": 0.3768450184501845, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "learning_rate": 0.0002577742946708464, | |
| "loss": 0.1805, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 17.84, | |
| "learning_rate": 0.0002562068965517241, | |
| "loss": 0.1708, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 17.84, | |
| "eval_loss": 0.49353307485580444, | |
| "eval_runtime": 28.8557, | |
| "eval_samples_per_second": 7.382, | |
| "eval_steps_per_second": 0.936, | |
| "eval_wer": 0.3798431734317343, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 18.31, | |
| "learning_rate": 0.00025463949843260186, | |
| "loss": 0.1646, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 18.78, | |
| "learning_rate": 0.0002530721003134796, | |
| "loss": 0.1502, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 18.78, | |
| "eval_loss": 0.5329748392105103, | |
| "eval_runtime": 28.897, | |
| "eval_samples_per_second": 7.371, | |
| "eval_steps_per_second": 0.934, | |
| "eval_wer": 0.3886070110701107, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 19.25, | |
| "learning_rate": 0.00025150470219435734, | |
| "loss": 0.1508, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 0.0002499373040752351, | |
| "loss": 0.1498, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "eval_loss": 0.5085766315460205, | |
| "eval_runtime": 28.7784, | |
| "eval_samples_per_second": 7.401, | |
| "eval_steps_per_second": 0.938, | |
| "eval_wer": 0.37961254612546125, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 20.19, | |
| "learning_rate": 0.00024836990595611283, | |
| "loss": 0.1524, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 20.66, | |
| "learning_rate": 0.00024680250783699057, | |
| "loss": 0.1517, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 20.66, | |
| "eval_loss": 0.5103166699409485, | |
| "eval_runtime": 28.7711, | |
| "eval_samples_per_second": 7.403, | |
| "eval_steps_per_second": 0.938, | |
| "eval_wer": 0.3828413284132841, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 21.13, | |
| "learning_rate": 0.0002452351097178683, | |
| "loss": 0.1637, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 0.00024366771159874606, | |
| "loss": 0.1376, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "eval_loss": 0.5393425226211548, | |
| "eval_runtime": 28.8325, | |
| "eval_samples_per_second": 7.388, | |
| "eval_steps_per_second": 0.936, | |
| "eval_wer": 0.375, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 22.07, | |
| "learning_rate": 0.00024210031347962383, | |
| "loss": 0.1332, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 22.54, | |
| "learning_rate": 0.00024053291536050154, | |
| "loss": 0.12, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 22.54, | |
| "eval_loss": 0.550984263420105, | |
| "eval_runtime": 28.8353, | |
| "eval_samples_per_second": 7.387, | |
| "eval_steps_per_second": 0.936, | |
| "eval_wer": 0.37915129151291516, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 0.0002389655172413793, | |
| "loss": 0.1428, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 23.47, | |
| "learning_rate": 0.00023739811912225703, | |
| "loss": 0.1293, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 23.47, | |
| "eval_loss": 0.5512908101081848, | |
| "eval_runtime": 28.7565, | |
| "eval_samples_per_second": 7.407, | |
| "eval_steps_per_second": 0.939, | |
| "eval_wer": 0.3731549815498155, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 23.94, | |
| "learning_rate": 0.00023583072100313477, | |
| "loss": 0.1329, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 24.41, | |
| "learning_rate": 0.0002342633228840125, | |
| "loss": 0.1228, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 24.41, | |
| "eval_loss": 0.5537130236625671, | |
| "eval_runtime": 28.9207, | |
| "eval_samples_per_second": 7.365, | |
| "eval_steps_per_second": 0.934, | |
| "eval_wer": 0.37615313653136534, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 24.88, | |
| "learning_rate": 0.00023269592476489026, | |
| "loss": 0.1232, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 25.35, | |
| "learning_rate": 0.00023112852664576802, | |
| "loss": 0.1116, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 25.35, | |
| "eval_loss": 0.557085394859314, | |
| "eval_runtime": 29.0557, | |
| "eval_samples_per_second": 7.331, | |
| "eval_steps_per_second": 0.929, | |
| "eval_wer": 0.37107933579335795, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 25.82, | |
| "learning_rate": 0.00022956112852664574, | |
| "loss": 0.1226, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 26.29, | |
| "learning_rate": 0.0002279937304075235, | |
| "loss": 0.1135, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 26.29, | |
| "eval_loss": 0.5842786431312561, | |
| "eval_runtime": 28.9955, | |
| "eval_samples_per_second": 7.346, | |
| "eval_steps_per_second": 0.931, | |
| "eval_wer": 0.37546125461254615, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 26.76, | |
| "learning_rate": 0.00022642633228840123, | |
| "loss": 0.1275, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 27.23, | |
| "learning_rate": 0.00022485893416927897, | |
| "loss": 0.1107, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 27.23, | |
| "eval_loss": 0.5824669599533081, | |
| "eval_runtime": 28.8912, | |
| "eval_samples_per_second": 7.372, | |
| "eval_steps_per_second": 0.935, | |
| "eval_wer": 0.37661439114391143, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 27.7, | |
| "learning_rate": 0.0002232915360501567, | |
| "loss": 0.1201, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 28.17, | |
| "learning_rate": 0.00022172413793103445, | |
| "loss": 0.1086, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 28.17, | |
| "eval_loss": 0.5459932684898376, | |
| "eval_runtime": 29.3059, | |
| "eval_samples_per_second": 7.268, | |
| "eval_steps_per_second": 0.921, | |
| "eval_wer": 0.37038745387453875, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 28.64, | |
| "learning_rate": 0.00022015673981191222, | |
| "loss": 0.0977, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 29.11, | |
| "learning_rate": 0.00021858934169278994, | |
| "loss": 0.1055, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 29.11, | |
| "eval_loss": 0.5809206366539001, | |
| "eval_runtime": 29.2262, | |
| "eval_samples_per_second": 7.288, | |
| "eval_steps_per_second": 0.924, | |
| "eval_wer": 0.3694649446494465, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 29.58, | |
| "learning_rate": 0.0002170219435736677, | |
| "loss": 0.1084, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 30.05, | |
| "learning_rate": 0.00021545454545454542, | |
| "loss": 0.1139, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 30.05, | |
| "eval_loss": 0.5718210935592651, | |
| "eval_runtime": 29.1425, | |
| "eval_samples_per_second": 7.309, | |
| "eval_steps_per_second": 0.926, | |
| "eval_wer": 0.37845940959409596, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 30.52, | |
| "learning_rate": 0.0002138871473354232, | |
| "loss": 0.1026, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 30.99, | |
| "learning_rate": 0.00021231974921630094, | |
| "loss": 0.1152, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 30.99, | |
| "eval_loss": 0.584858775138855, | |
| "eval_runtime": 28.8726, | |
| "eval_samples_per_second": 7.377, | |
| "eval_steps_per_second": 0.935, | |
| "eval_wer": 0.36300738007380073, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 31.46, | |
| "learning_rate": 0.00021075235109717865, | |
| "loss": 0.0929, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 31.92, | |
| "learning_rate": 0.00020918495297805642, | |
| "loss": 0.0959, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 31.92, | |
| "eval_loss": 0.5689957737922668, | |
| "eval_runtime": 29.1034, | |
| "eval_samples_per_second": 7.319, | |
| "eval_steps_per_second": 0.928, | |
| "eval_wer": 0.3706180811808118, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 32.39, | |
| "learning_rate": 0.00020761755485893414, | |
| "loss": 0.0958, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "learning_rate": 0.0002060501567398119, | |
| "loss": 0.0913, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "eval_loss": 0.5901004076004028, | |
| "eval_runtime": 29.0974, | |
| "eval_samples_per_second": 7.32, | |
| "eval_steps_per_second": 0.928, | |
| "eval_wer": 0.36185424354243545, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 0.00020448275862068962, | |
| "loss": 0.0946, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 33.8, | |
| "learning_rate": 0.0002029153605015674, | |
| "loss": 0.0876, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 33.8, | |
| "eval_loss": 0.5581740140914917, | |
| "eval_runtime": 29.0897, | |
| "eval_samples_per_second": 7.322, | |
| "eval_steps_per_second": 0.928, | |
| "eval_wer": 0.3634686346863469, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 34.27, | |
| "learning_rate": 0.00020134796238244513, | |
| "loss": 0.094, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 34.74, | |
| "learning_rate": 0.00019978056426332285, | |
| "loss": 0.0999, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 34.74, | |
| "eval_loss": 0.5737707018852234, | |
| "eval_runtime": 29.1504, | |
| "eval_samples_per_second": 7.307, | |
| "eval_steps_per_second": 0.926, | |
| "eval_wer": 0.36185424354243545, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 35.21, | |
| "learning_rate": 0.00019821316614420062, | |
| "loss": 0.0855, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 35.68, | |
| "learning_rate": 0.00019664576802507833, | |
| "loss": 0.0844, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 35.68, | |
| "eval_loss": 0.5892208218574524, | |
| "eval_runtime": 29.199, | |
| "eval_samples_per_second": 7.295, | |
| "eval_steps_per_second": 0.925, | |
| "eval_wer": 0.3521678966789668, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 36.15, | |
| "learning_rate": 0.0001950783699059561, | |
| "loss": 0.0881, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 36.62, | |
| "learning_rate": 0.00019351097178683382, | |
| "loss": 0.0774, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 36.62, | |
| "eval_loss": 0.6038769483566284, | |
| "eval_runtime": 29.1467, | |
| "eval_samples_per_second": 7.308, | |
| "eval_steps_per_second": 0.926, | |
| "eval_wer": 0.36485239852398527, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 37.09, | |
| "learning_rate": 0.0001919435736677116, | |
| "loss": 0.0793, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 37.56, | |
| "learning_rate": 0.00019037617554858933, | |
| "loss": 0.0944, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 37.56, | |
| "eval_loss": 0.580478310585022, | |
| "eval_runtime": 29.0539, | |
| "eval_samples_per_second": 7.331, | |
| "eval_steps_per_second": 0.929, | |
| "eval_wer": 0.36047047970479706, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 38.03, | |
| "learning_rate": 0.00018880877742946707, | |
| "loss": 0.078, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 38.5, | |
| "learning_rate": 0.00018724137931034482, | |
| "loss": 0.0803, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 38.5, | |
| "eval_loss": 0.5946702361106873, | |
| "eval_runtime": 29.1085, | |
| "eval_samples_per_second": 7.317, | |
| "eval_steps_per_second": 0.928, | |
| "eval_wer": 0.3514760147601476, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 38.97, | |
| "learning_rate": 0.00018567398119122253, | |
| "loss": 0.0779, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 39.44, | |
| "learning_rate": 0.0001841065830721003, | |
| "loss": 0.0721, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 39.44, | |
| "eval_loss": 0.6369604468345642, | |
| "eval_runtime": 29.163, | |
| "eval_samples_per_second": 7.304, | |
| "eval_steps_per_second": 0.926, | |
| "eval_wer": 0.36531365313653136, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 39.91, | |
| "learning_rate": 0.00018253918495297804, | |
| "loss": 0.0783, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 40.38, | |
| "learning_rate": 0.0001809717868338558, | |
| "loss": 0.0854, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 40.38, | |
| "eval_loss": 0.6401636600494385, | |
| "eval_runtime": 29.0975, | |
| "eval_samples_per_second": 7.32, | |
| "eval_steps_per_second": 0.928, | |
| "eval_wer": 0.3613929889298893, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 40.85, | |
| "learning_rate": 0.00017940438871473353, | |
| "loss": 0.0719, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 41.31, | |
| "learning_rate": 0.00017783699059561127, | |
| "loss": 0.0775, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 41.31, | |
| "eval_loss": 0.6300048828125, | |
| "eval_runtime": 29.124, | |
| "eval_samples_per_second": 7.314, | |
| "eval_steps_per_second": 0.927, | |
| "eval_wer": 0.35724169741697415, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 41.78, | |
| "learning_rate": 0.00017626959247648901, | |
| "loss": 0.0747, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 42.25, | |
| "learning_rate": 0.00017470219435736673, | |
| "loss": 0.073, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 42.25, | |
| "eval_loss": 0.6028448343276978, | |
| "eval_runtime": 29.1165, | |
| "eval_samples_per_second": 7.315, | |
| "eval_steps_per_second": 0.927, | |
| "eval_wer": 0.3547047970479705, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 42.72, | |
| "learning_rate": 0.0001731347962382445, | |
| "loss": 0.0608, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 43.19, | |
| "learning_rate": 0.00017156739811912227, | |
| "loss": 0.0591, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 43.19, | |
| "eval_loss": 0.6349148750305176, | |
| "eval_runtime": 28.9365, | |
| "eval_samples_per_second": 7.361, | |
| "eval_steps_per_second": 0.933, | |
| "eval_wer": 0.36531365313653136, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 43.66, | |
| "learning_rate": 0.00016999999999999999, | |
| "loss": 0.0766, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 44.13, | |
| "learning_rate": 0.00016843260188087773, | |
| "loss": 0.0641, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 44.13, | |
| "eval_loss": 0.6087113618850708, | |
| "eval_runtime": 29.0785, | |
| "eval_samples_per_second": 7.325, | |
| "eval_steps_per_second": 0.929, | |
| "eval_wer": 0.35447416974169743, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 44.6, | |
| "learning_rate": 0.00016686520376175547, | |
| "loss": 0.0672, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 45.07, | |
| "learning_rate": 0.0001652978056426332, | |
| "loss": 0.0731, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 45.07, | |
| "eval_loss": 0.6003465056419373, | |
| "eval_runtime": 29.0263, | |
| "eval_samples_per_second": 7.338, | |
| "eval_steps_per_second": 0.93, | |
| "eval_wer": 0.36300738007380073, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 45.54, | |
| "learning_rate": 0.00016373040752351096, | |
| "loss": 0.0658, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 0.0001621630094043887, | |
| "loss": 0.0651, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "eval_loss": 0.6361915469169617, | |
| "eval_runtime": 29.5463, | |
| "eval_samples_per_second": 7.209, | |
| "eval_steps_per_second": 0.914, | |
| "eval_wer": 0.34940036900369004, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 46.48, | |
| "learning_rate": 0.00016059561128526647, | |
| "loss": 0.064, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 46.95, | |
| "learning_rate": 0.00015902821316614418, | |
| "loss": 0.0679, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 46.95, | |
| "eval_loss": 0.6263274550437927, | |
| "eval_runtime": 29.0253, | |
| "eval_samples_per_second": 7.338, | |
| "eval_steps_per_second": 0.93, | |
| "eval_wer": 0.3551660516605166, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 47.42, | |
| "learning_rate": 0.00015746081504702193, | |
| "loss": 0.0589, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 47.89, | |
| "learning_rate": 0.00015589341692789967, | |
| "loss": 0.0716, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 47.89, | |
| "eval_loss": 0.6083901524543762, | |
| "eval_runtime": 29.0652, | |
| "eval_samples_per_second": 7.328, | |
| "eval_steps_per_second": 0.929, | |
| "eval_wer": 0.3526291512915129, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 48.36, | |
| "learning_rate": 0.0001543260188087774, | |
| "loss": 0.073, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 48.83, | |
| "learning_rate": 0.00015275862068965518, | |
| "loss": 0.066, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 48.83, | |
| "eval_loss": 0.6158061027526855, | |
| "eval_runtime": 29.3027, | |
| "eval_samples_per_second": 7.269, | |
| "eval_steps_per_second": 0.921, | |
| "eval_wer": 0.3563191881918819, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 49.3, | |
| "learning_rate": 0.0001511912225705329, | |
| "loss": 0.0581, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 49.77, | |
| "learning_rate": 0.00014962382445141064, | |
| "loss": 0.0564, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 49.77, | |
| "eval_loss": 0.6484010815620422, | |
| "eval_runtime": 29.5466, | |
| "eval_samples_per_second": 7.209, | |
| "eval_steps_per_second": 0.914, | |
| "eval_wer": 0.35793357933579334, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 50.23, | |
| "learning_rate": 0.00014805642633228838, | |
| "loss": 0.0585, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 50.7, | |
| "learning_rate": 0.00014648902821316615, | |
| "loss": 0.0679, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 50.7, | |
| "eval_loss": 0.6405696868896484, | |
| "eval_runtime": 29.3581, | |
| "eval_samples_per_second": 7.255, | |
| "eval_steps_per_second": 0.92, | |
| "eval_wer": 0.3549354243542435, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 51.17, | |
| "learning_rate": 0.00014492163009404387, | |
| "loss": 0.0573, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 51.64, | |
| "learning_rate": 0.0001433542319749216, | |
| "loss": 0.061, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 51.64, | |
| "eval_loss": 0.6469581127166748, | |
| "eval_runtime": 29.5701, | |
| "eval_samples_per_second": 7.203, | |
| "eval_steps_per_second": 0.913, | |
| "eval_wer": 0.3533210332103321, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 52.11, | |
| "learning_rate": 0.00014178683385579935, | |
| "loss": 0.0582, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 52.58, | |
| "learning_rate": 0.0001402194357366771, | |
| "loss": 0.0566, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 52.58, | |
| "eval_loss": 0.659860372543335, | |
| "eval_runtime": 29.2997, | |
| "eval_samples_per_second": 7.27, | |
| "eval_steps_per_second": 0.922, | |
| "eval_wer": 0.3514760147601476, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 53.05, | |
| "learning_rate": 0.00013865203761755484, | |
| "loss": 0.0552, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 53.52, | |
| "learning_rate": 0.0001370846394984326, | |
| "loss": 0.0614, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 53.52, | |
| "eval_loss": 0.6916360855102539, | |
| "eval_runtime": 29.2037, | |
| "eval_samples_per_second": 7.294, | |
| "eval_steps_per_second": 0.925, | |
| "eval_wer": 0.3570110701107011, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 53.99, | |
| "learning_rate": 0.00013551724137931035, | |
| "loss": 0.0588, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 54.46, | |
| "learning_rate": 0.00013394984326018806, | |
| "loss": 0.0567, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 54.46, | |
| "eval_loss": 0.6793951988220215, | |
| "eval_runtime": 29.1822, | |
| "eval_samples_per_second": 7.299, | |
| "eval_steps_per_second": 0.925, | |
| "eval_wer": 0.3503228782287823, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 54.93, | |
| "learning_rate": 0.0001323824451410658, | |
| "loss": 0.0598, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 55.4, | |
| "learning_rate": 0.00013081504702194355, | |
| "loss": 0.0548, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 55.4, | |
| "eval_loss": 0.6582257151603699, | |
| "eval_runtime": 29.0712, | |
| "eval_samples_per_second": 7.327, | |
| "eval_steps_per_second": 0.929, | |
| "eval_wer": 0.3556273062730627, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 55.87, | |
| "learning_rate": 0.0001292476489028213, | |
| "loss": 0.0587, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 56.34, | |
| "learning_rate": 0.00012768025078369906, | |
| "loss": 0.052, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 56.34, | |
| "eval_loss": 0.6707574725151062, | |
| "eval_runtime": 29.1671, | |
| "eval_samples_per_second": 7.303, | |
| "eval_steps_per_second": 0.926, | |
| "eval_wer": 0.34870848708487084, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 56.81, | |
| "learning_rate": 0.0001261128526645768, | |
| "loss": 0.0544, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 57.28, | |
| "learning_rate": 0.00012454545454545455, | |
| "loss": 0.058, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 57.28, | |
| "eval_loss": 0.6558502912521362, | |
| "eval_runtime": 29.1303, | |
| "eval_samples_per_second": 7.312, | |
| "eval_steps_per_second": 0.927, | |
| "eval_wer": 0.3507841328413284, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 57.75, | |
| "learning_rate": 0.0001229780564263323, | |
| "loss": 0.0476, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 58.22, | |
| "learning_rate": 0.00012141065830721002, | |
| "loss": 0.0558, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 58.22, | |
| "eval_loss": 0.6627236008644104, | |
| "eval_runtime": 29.1431, | |
| "eval_samples_per_second": 7.309, | |
| "eval_steps_per_second": 0.926, | |
| "eval_wer": 0.35239852398523985, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 58.69, | |
| "learning_rate": 0.00011984326018808776, | |
| "loss": 0.0524, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 59.15, | |
| "learning_rate": 0.0001182758620689655, | |
| "loss": 0.0567, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 59.15, | |
| "eval_loss": 0.6643950343132019, | |
| "eval_runtime": 29.149, | |
| "eval_samples_per_second": 7.307, | |
| "eval_steps_per_second": 0.926, | |
| "eval_wer": 0.3512453874538745, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 59.62, | |
| "learning_rate": 0.00011670846394984326, | |
| "loss": 0.048, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 60.09, | |
| "learning_rate": 0.000115141065830721, | |
| "loss": 0.0551, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 60.09, | |
| "eval_loss": 0.6813772916793823, | |
| "eval_runtime": 29.2298, | |
| "eval_samples_per_second": 7.287, | |
| "eval_steps_per_second": 0.924, | |
| "eval_wer": 0.3484778597785978, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 60.56, | |
| "learning_rate": 0.00011357366771159873, | |
| "loss": 0.0515, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 61.03, | |
| "learning_rate": 0.00011200626959247647, | |
| "loss": 0.0467, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 61.03, | |
| "eval_loss": 0.7115447521209717, | |
| "eval_runtime": 29.1151, | |
| "eval_samples_per_second": 7.316, | |
| "eval_steps_per_second": 0.927, | |
| "eval_wer": 0.34801660516605165, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 61.5, | |
| "learning_rate": 0.00011043887147335422, | |
| "loss": 0.0472, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 61.97, | |
| "learning_rate": 0.00010887147335423196, | |
| "loss": 0.0487, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 61.97, | |
| "eval_loss": 0.6461969614028931, | |
| "eval_runtime": 29.2046, | |
| "eval_samples_per_second": 7.293, | |
| "eval_steps_per_second": 0.925, | |
| "eval_wer": 0.34870848708487084, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 62.44, | |
| "learning_rate": 0.00010730407523510972, | |
| "loss": 0.0497, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 62.91, | |
| "learning_rate": 0.00010573667711598746, | |
| "loss": 0.0554, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 62.91, | |
| "eval_loss": 0.6031398773193359, | |
| "eval_runtime": 29.1799, | |
| "eval_samples_per_second": 7.3, | |
| "eval_steps_per_second": 0.925, | |
| "eval_wer": 0.34686346863468637, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 63.38, | |
| "learning_rate": 0.0001041692789968652, | |
| "loss": 0.0435, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 63.85, | |
| "learning_rate": 0.00010260188087774294, | |
| "loss": 0.0513, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 63.85, | |
| "eval_loss": 0.6592887043952942, | |
| "eval_runtime": 29.1723, | |
| "eval_samples_per_second": 7.301, | |
| "eval_steps_per_second": 0.926, | |
| "eval_wer": 0.34801660516605165, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 64.32, | |
| "learning_rate": 0.00010103448275862067, | |
| "loss": 0.0501, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 64.79, | |
| "learning_rate": 9.946708463949841e-05, | |
| "loss": 0.0484, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 64.79, | |
| "eval_loss": 0.6585196852684021, | |
| "eval_runtime": 29.3855, | |
| "eval_samples_per_second": 7.248, | |
| "eval_steps_per_second": 0.919, | |
| "eval_wer": 0.34432656826568264, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 65.26, | |
| "learning_rate": 9.789968652037617e-05, | |
| "loss": 0.0449, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 65.73, | |
| "learning_rate": 9.633228840125391e-05, | |
| "loss": 0.043, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 65.73, | |
| "eval_loss": 0.6810497641563416, | |
| "eval_runtime": 29.273, | |
| "eval_samples_per_second": 7.276, | |
| "eval_steps_per_second": 0.922, | |
| "eval_wer": 0.3404059040590406, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 66.2, | |
| "learning_rate": 9.476489028213166e-05, | |
| "loss": 0.0494, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "learning_rate": 9.31974921630094e-05, | |
| "loss": 0.0487, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "eval_loss": 0.6745949387550354, | |
| "eval_runtime": 29.2853, | |
| "eval_samples_per_second": 7.273, | |
| "eval_steps_per_second": 0.922, | |
| "eval_wer": 0.3507841328413284, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 67.14, | |
| "learning_rate": 9.163009404388714e-05, | |
| "loss": 0.0428, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 67.61, | |
| "learning_rate": 9.006269592476488e-05, | |
| "loss": 0.0421, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 67.61, | |
| "eval_loss": 0.6884201169013977, | |
| "eval_runtime": 29.0927, | |
| "eval_samples_per_second": 7.321, | |
| "eval_steps_per_second": 0.928, | |
| "eval_wer": 0.3514760147601476, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 68.08, | |
| "learning_rate": 8.849529780564261e-05, | |
| "loss": 0.045, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 68.54, | |
| "learning_rate": 8.692789968652037e-05, | |
| "loss": 0.0475, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 68.54, | |
| "eval_loss": 0.6797507405281067, | |
| "eval_runtime": 29.0724, | |
| "eval_samples_per_second": 7.327, | |
| "eval_steps_per_second": 0.929, | |
| "eval_wer": 0.34801660516605165, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 69.01, | |
| "learning_rate": 8.536050156739811e-05, | |
| "loss": 0.0475, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 69.48, | |
| "learning_rate": 8.379310344827585e-05, | |
| "loss": 0.0423, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 69.48, | |
| "eval_loss": 0.7019987106323242, | |
| "eval_runtime": 29.1029, | |
| "eval_samples_per_second": 7.319, | |
| "eval_steps_per_second": 0.928, | |
| "eval_wer": 0.3484778597785978, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 69.95, | |
| "learning_rate": 8.22257053291536e-05, | |
| "loss": 0.0418, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 70.42, | |
| "learning_rate": 8.065830721003134e-05, | |
| "loss": 0.0483, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 70.42, | |
| "eval_loss": 0.6741328835487366, | |
| "eval_runtime": 29.3432, | |
| "eval_samples_per_second": 7.259, | |
| "eval_steps_per_second": 0.92, | |
| "eval_wer": 0.3482472324723247, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 70.89, | |
| "learning_rate": 7.909090909090908e-05, | |
| "loss": 0.0437, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 71.36, | |
| "learning_rate": 7.752351097178684e-05, | |
| "loss": 0.0435, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 71.36, | |
| "eval_loss": 0.693108081817627, | |
| "eval_runtime": 29.4586, | |
| "eval_samples_per_second": 7.23, | |
| "eval_steps_per_second": 0.917, | |
| "eval_wer": 0.34086715867158673, | |
| "step": 7600 | |
| } | |
| ], | |
| "max_steps": 10070, | |
| "num_train_epochs": 95, | |
| "total_flos": 3.519219302842646e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |